18817147. Debiasing Pre-trained Sentence Encoders With Probabilistic Dropouts (Oracle International Corporation)
Contents
Debiasing Pre-trained Sentence Encoders With Probabilistic Dropouts
Organization Name
Oracle International Corporation
Inventor(s)
Swetasudha Panda of Burlington MA (US)
Ariel Kobren of Cambridge MA (US)
Michael Louis Wick of Lexington MA (US)
Stephen Green of Burlington MA (US)
Debiasing Pre-trained Sentence Encoders With Probabilistic Dropouts
This abstract first appeared for US patent application 18817147 titled 'Debiasing Pre-trained Sentence Encoders With Probabilistic Dropouts
Original Abstract Submitted
Debiasing pre-trained sentence encoders with probabilistic dropouts may be performed by various systems, services, or applications. A sentence may be received, where the words of the sentence may be provided as tokens to an encoder of a machine learning model. A token-wise correlation using semantic orientation may be determined to determine a bias score for the tokens in the input sentence. A probability of dropout that for tokens in the input sentence may be determined from the bias scores. The machine learning model may be trained or tuned based on the probabilities of dropout for the tokens in the input sentence.
